arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.01638cs.HC
收藏

谁向我解释隐私政策?基于大型语言模型的虚拟现实隐私助手

Who Explains Privacy Policies to Me? Embodied and Textual LLM-Powered Privacy Assistants in Virtual Reality

Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Leipzig University(莱比锡大学可扩展数据分析与人工智能中心);LMU Munich(慕尼黑大学);University of the Bundeswehr Munich(联邦国防军慕尼黑大学)

Vincent Freiberger, Moritz Dresch, Florian Alt, Arthur Fleig, Viktorija Paneva

AI总结:

本研究提出基于大型语言模型的虚拟现实隐私助手,通过文本和具身交互模式提升用户对隐私政策的理解和决策质量。

摘要:

虚拟现实(VR)系统收集细粒度的行为和生物数据,但隐私政策很少被阅读或理解,因为其语言复杂、篇幅长且与用户的交互流程整合不佳。为了在选择点降低知情同意的门槛,我们探索了一种基于大型语言模型(LLM)的隐私助手,嵌入到VR应用商店中,以支持隐私意识的应用选择。助手实现了两种交互模式:基于文本的聊天界面和提供口头解释的具身虚拟虚拟角色。我们报告了一项探索性内组研究(N=21),参与者在无协助和有协助条件下浏览VR生产力应用。我们的发现表明,两种交互模式都支持更谨慎地与隐私信息和决策互动,隐私分数主要起 veto 机制作用而非主要选择驱动因素。具身交互的影响因参与者而异,而文本交互支持反思性审查。

英文摘要:

Virtual Reality (VR) systems collect fine-grained behavioral and biometric data, yet privacy policies are rarely read or understood due to their complex language, length, and poor integration into users' interaction workflows. To lower the barrier to informed consent at the point of choice, we explore a Large Language Model (LLM)-powered privacy assistant embedded into a VR app store to support privacy-aware app selection. The assistant is realized in two interaction modes: a text-based chat interface and an embodied virtual avatar providing spoken explanations. We report on an exploratory within-subjects study $(N = 21)$ in which participants browsed VR productivity applications under unassisted and assisted conditions. Our findings suggest that both interaction modes support more deliberate engagement with privacy information and decision-making, with privacy scores primarily functioning as a veto mechanism rather than a primary selection driver. The impact of embodied interaction varied between participants, while textual interaction supported reflective review.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑